commit ec826e1e3193a0c45d769f4c030db69920ade214 Author: ModelHub XC Date: Sun Apr 12 22:05:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..95318ec --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-0.6B-Medical-Expert.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-0.6B-Medical-Expert.i1-IQ1_M.gguf b/Qwen3-0.6B-Medical-Expert.i1-IQ1_M.gguf new file mode 100644 index 0000000..6d26a0d --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c19c767ad9f534da00983d8589f2640562b3558e8227a8970b8bdfec08c69bc3 +size 216053440 diff --git a/Qwen3-0.6B-Medical-Expert.i1-IQ1_S.gguf b/Qwen3-0.6B-Medical-Expert.i1-IQ1_S.gguf new file mode 100644 index 0000000..054bb61 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e12fbc60e00d6948a82ba72fd675949c493829264023061523a211ee7a160330 +size 208017088 diff --git a/Qwen3-0.6B-Medical-Expert.i1-IQ2_M.gguf b/Qwen3-0.6B-Medical-Expert.i1-IQ2_M.gguf new file mode 100644 index 0000000..eb7595d --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75da06f7e466d7c5a2f8420f4e69b56075c886c5e21e011af1ad0208f07ef8aa +size 264910528 diff --git a/Qwen3-0.6B-Medical-Expert.i1-IQ2_S.gguf b/Qwen3-0.6B-Medical-Expert.i1-IQ2_S.gguf new file mode 100644 index 0000000..df4d951 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d9ade683919294b21e80eb700a0c78a226413fac9ffc3a6ddd1d4b6f844a8e5 +size 254195392 diff --git a/Qwen3-0.6B-Medical-Expert.i1-IQ2_XS.gguf b/Qwen3-0.6B-Medical-Expert.i1-IQ2_XS.gguf new file mode 100644 index 0000000..287a4cb --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5147c1f6f1d71b6f96a2c9b83bc949830e7af8f7a9a02769af91eadc28edca8 +size 241997504 diff --git a/Qwen3-0.6B-Medical-Expert.i1-IQ2_XXS.gguf b/Qwen3-0.6B-Medical-Expert.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8fac046 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0f80ba301ce7bedf65486ebb2f3886ee1ace1296fa0d6fa2f38709b172dea4c +size 229447360 diff --git a/Qwen3-0.6B-Medical-Expert.i1-IQ3_M.gguf b/Qwen3-0.6B-Medical-Expert.i1-IQ3_M.gguf new file mode 100644 index 0000000..9959dd6 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d0141d8e8e9e40a54014454e36af50c8d474805063ad15b04b87c866274d7d +size 336028352 diff --git a/Qwen3-0.6B-Medical-Expert.i1-IQ3_S.gguf b/Qwen3-0.6B-Medical-Expert.i1-IQ3_S.gguf new file mode 100644 index 0000000..9706f4f --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dbc004367c01ab6dce8e06522ec994e14a2d03187f33fa90b3aaa62cb7d4361 +size 323076800 diff --git a/Qwen3-0.6B-Medical-Expert.i1-IQ3_XS.gguf b/Qwen3-0.6B-Medical-Expert.i1-IQ3_XS.gguf new file mode 100644 index 0000000..8332e9e --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf30cfbe52302ec18e893cd963973f7986a2900ecbb48aafb8472b5ab4c4b59 +size 312754880 diff --git a/Qwen3-0.6B-Medical-Expert.i1-IQ3_XXS.gguf b/Qwen3-0.6B-Medical-Expert.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e62a3e2 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb8168563d01259d7134764509d58ef02d0425f7fc0bd2fc041615eb1706c961 +size 279017152 diff --git a/Qwen3-0.6B-Medical-Expert.i1-IQ4_NL.gguf b/Qwen3-0.6B-Medical-Expert.i1-IQ4_NL.gguf new file mode 100644 index 0000000..e4b15b8 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab15013d7d928e4b2645d91800fae6be35a4ef46a04c2828daaac49a17310b86 +size 381567680 diff --git a/Qwen3-0.6B-Medical-Expert.i1-IQ4_XS.gguf b/Qwen3-0.6B-Medical-Expert.i1-IQ4_XS.gguf new file mode 100644 index 0000000..afa9bef --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7b710c62567a366e1e6f24465dfde42da95b32eb0dbec2bfc50c01434cb6fba +size 367805120 diff --git a/Qwen3-0.6B-Medical-Expert.i1-Q2_K.gguf b/Qwen3-0.6B-Medical-Expert.i1-Q2_K.gguf new file mode 100644 index 0000000..7122dbf --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3ca14654e92289017ff41ebbd5d1d084f5c908b833b84528bc7066ed941e1e2 +size 296239808 diff --git a/Qwen3-0.6B-Medical-Expert.i1-Q2_K_S.gguf b/Qwen3-0.6B-Medical-Expert.i1-Q2_K_S.gguf new file mode 100644 index 0000000..ba455ad --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8046b32af84962b91ee446753ed9f958e0e58033aaf10b94e217ac0c55f5918 +size 280560320 diff --git a/Qwen3-0.6B-Medical-Expert.i1-Q3_K_L.gguf b/Qwen3-0.6B-Medical-Expert.i1-Q3_K_L.gguf new file mode 100644 index 0000000..f8ef3c9 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc5e08d213acbe5e1a07e3e66017ab6636837d52412d64f708ea6b2121b61344 +size 368493248 diff --git a/Qwen3-0.6B-Medical-Expert.i1-Q3_K_M.gguf b/Qwen3-0.6B-Medical-Expert.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1ff24c5 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:895880d3adc3690346b3c541b66feb792775ce95e3c5ed76b4e04828302ddcea +size 347128512 diff --git a/Qwen3-0.6B-Medical-Expert.i1-Q3_K_S.gguf b/Qwen3-0.6B-Medical-Expert.i1-Q3_K_S.gguf new file mode 100644 index 0000000..f92318c --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbbcc7efe77a48c574be24e985bb8f381c636dd8f2abe9603f69dda4afdef332 +size 323076800 diff --git a/Qwen3-0.6B-Medical-Expert.i1-Q4_0.gguf b/Qwen3-0.6B-Medical-Expert.i1-Q4_0.gguf new file mode 100644 index 0000000..9f27ff3 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bbae73a3949add1669cf28dfb7d73341d6900f6c87455cce7e2379ad3699020 +size 382157504 diff --git a/Qwen3-0.6B-Medical-Expert.i1-Q4_1.gguf b/Qwen3-0.6B-Medical-Expert.i1-Q4_1.gguf new file mode 100644 index 0000000..b2e4c2d --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bee1ec78f533f7d0606e05f2173077404c910e9db02fd5f32b022d12b4047d7 +size 409092800 diff --git a/Qwen3-0.6B-Medical-Expert.i1-Q4_K_M.gguf b/Qwen3-0.6B-Medical-Expert.i1-Q4_K_M.gguf new file mode 100644 index 0000000..3556c16 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86b00be5699435c37d65d019441167b6adcab68323cdf26e2c09f81be4ce0c06 +size 396706496 diff --git a/Qwen3-0.6B-Medical-Expert.i1-Q4_K_S.gguf b/Qwen3-0.6B-Medical-Expert.i1-Q4_K_S.gguf new file mode 100644 index 0000000..89e7469 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b155c99a4dee0a53cdb48f233c71119fb9ed660dbb265fc2a2983f2bc10555 +size 383271616 diff --git a/Qwen3-0.6B-Medical-Expert.i1-Q5_K_M.gguf b/Qwen3-0.6B-Medical-Expert.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6962f57 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a9ffcd765130eacafd71e4b615ebce58aa0105232a28a2352925fea84afdf6f +size 444416704 diff --git a/Qwen3-0.6B-Medical-Expert.i1-Q5_K_S.gguf b/Qwen3-0.6B-Medical-Expert.i1-Q5_K_S.gguf new file mode 100644 index 0000000..daf5a16 --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12ca5564b01babb3881e12bce9bc59432793f2f5788dadf45c33860c926580c5 +size 436617920 diff --git a/Qwen3-0.6B-Medical-Expert.i1-Q6_K.gguf b/Qwen3-0.6B-Medical-Expert.i1-Q6_K.gguf new file mode 100644 index 0000000..978bdbb --- /dev/null +++ b/Qwen3-0.6B-Medical-Expert.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46e9f59fa9fc99c2a838e27d9da85b394e6b2ff838920b5945beb06494a2998e +size 495108800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9967a95 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: suayptalha/Qwen3-0.6B-Medical-Expert +datasets: +- FreedomIntelligence/medical-o1-reasoning-SFT +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +- medical +- reasoning +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/suayptalha/Qwen3-0.6B-Medical-Expert + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-0.6B-Medical-Expert-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-IQ1_S.gguf) | i1-IQ1_S | 0.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-IQ1_M.gguf) | i1-IQ1_M | 0.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-Q4_1.gguf) | i1-Q4_1 | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-Medical-Expert-i1-GGUF/resolve/main/Qwen3-0.6B-Medical-Expert.i1-Q6_K.gguf) | i1-Q6_K | 0.6 | practically like static Q6_K | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..6fcab0a --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a008a43e201399d61d8c13fbe786a72981a619893b6e5e6f34eb0a381105bf +size 1153369